aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorSergey M. <dstftw@gmail.com>2014-02-28 22:52:06 +0700
committerSergey M. <dstftw@gmail.com>2014-02-28 22:52:06 +0700
commitfc26f3b4c2bd86bef11829d21985d53bf21bd676 (patch)
treed2a13d430da3ae747aa1e2a74d26f04f5e5b3093 /youtube_dl
parentf604c93c64df542de6921bc071f47c205742fe77 (diff)
[lifenews] Add support for multiple videos on the same page (#2482)
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/lifenews.py37
1 files changed, 21 insertions, 16 deletions
diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py
index bb1bae643..7a431a274 100644
--- a/youtube_dl/extractor/lifenews.py
+++ b/youtube_dl/extractor/lifenews.py
@@ -6,7 +6,8 @@ import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
- unified_strdate
+ unified_strdate,
+ ExtractorError,
)
@@ -34,11 +35,9 @@ class LifeNewsIE(InfoExtractor):
webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
- video_url = self._html_search_regex(
- r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
-
- thumbnail = self._html_search_regex(
- r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+ videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
+ if not videos:
+ raise ExtractorError('No media links available for %s' % video_id)
title = self._og_search_title(webpage)
TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
@@ -57,13 +56,19 @@ class LifeNewsIE(InfoExtractor):
if upload_date is not None:
upload_date = unified_strdate(upload_date)
- return {
- 'id': video_id,
- 'url': video_url,
- 'thumbnail': thumbnail,
- 'title': title,
- 'description': description,
- 'view_count': int_or_none(view_count),
- 'comment_count': int_or_none(comment_count),
- 'upload_date': upload_date,
- } \ No newline at end of file
+ def make_entry(video_id, media, video_number=None):
+ return {
+ 'id': video_id,
+ 'url': media[1],
+ 'thumbnail': media[0],
+ 'title': title if video_number is None else '%s-video%s' % (title, video_number),
+ 'description': description,
+ 'view_count': int_or_none(view_count),
+ 'comment_count': int_or_none(comment_count),
+ 'upload_date': upload_date,
+ }
+
+ if len(videos) == 1:
+ return make_entry(video_id, videos[0])
+ else:
+ return [make_entry(video_id, media, video_number+1) for video_number, media in enumerate(videos)] \ No newline at end of file